{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T07:46:53Z","timestamp":1759132013740},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"5-6","license":[{"start":{"date-parts":[[2010,5,30]],"date-time":"2010-05-30T00:00:00Z","timestamp":1275177600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2010,10]]},"DOI":"10.1007\/s10766-010-0136-3","type":"journal-article","created":{"date-parts":[[2010,5,29]],"date-time":"2010-05-29T07:16:28Z","timestamp":1275117388000},"page":"418-439","source":"Crossref","is-referenced-by-count":54,"title":["ForestGOMP: An Efficient OpenMP Environment for NUMA Architectures"],"prefix":"10.1007","volume":"38","author":[{"given":"Fran\u00e7ois","family":"Broquedis","sequence":"first","affiliation":[]},{"given":"Nathalie","family":"Furmento","sequence":"additional","affiliation":[]},{"given":"Brice","family":"Goglin","sequence":"additional","affiliation":[]},{"given":"Pierre-Andr\u00e9","family":"Wacrenier","sequence":"additional","affiliation":[]},{"given":"Raymond","family":"Namyst","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2010,5,30]]},"reference":[{"key":"136_CR1","doi-asserted-by":"crossref","unstructured":"Antony, J., Janes, P.P., Rendell, A.P.: Exploring thread and memory placement on NUMA architectures: Solaris and Linux, UltraSPARC\/FirePlane and Opteron\/HyperTransport. In: Proceedings of the International Conference on High Performance Computing (HiPC). Bangalore, India (2006)","DOI":"10.1007\/11945918_35"},{"key":"136_CR2","doi-asserted-by":"crossref","unstructured":"Ayguade, E., Gonzalez, M., Martorell, X., Jost, G.: Employing nested OpenMP for the parallelization of multi-Zone computational fluid dynamics applications. In: 18th International Parallel and Distributed Processing Symposium (IPDPS) (2004)","DOI":"10.1109\/IPDPS.2004.1302905"},{"key":"136_CR3","doi-asserted-by":"crossref","unstructured":"Benkner, S., Brandes, T.: Efficient parallel programming on scalable shared memory systems with high performance fortran. In: Concurrency: Practice and Experience, vol. 14, pp. 789\u2013803. John Wiley & Sons (2002)","DOI":"10.1002\/cpe.649"},{"key":"136_CR4","unstructured":"Brecht, T.: On the importance of parallel application placement in NUMA multiprocessors. In: Proceedings of the Fourth Symposium on Experiences with Distributed and Multiprocessor Systems (SEDMS IV). San Diego, CA (1993)"},{"key":"136_CR5","doi-asserted-by":"crossref","unstructured":"Broquedis, F., Clet-Ortega, J., Moreaud, S., Furmento, N., Goglin, B., Mercier, G., Thibault, S., Namyst, R.: hwloc: a generic framework for managing hardware affinities in HPC applications. In: Proceedings of the 18th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP2010). IEEE Computer Society Press, Pisa, Italia (2010)","DOI":"10.1109\/PDP.2010.67"},{"key":"136_CR6","doi-asserted-by":"crossref","unstructured":"Broquedis, F., DiakhatT, F., Thibault, S., Aumage, O., Namyst, R., Wacrenier, P.A.: Scheduling Dynamic OpenMP Applications over Multicore Architectures. In: International Workshop on OpenMP (IWOMP). West Lafayette, IN (2008)","DOI":"10.1007\/978-3-540-79561-2_15"},{"key":"136_CR7","unstructured":"Carlson, W., Draper, J., Culler, D., Yelick, K., Brooks, E., Warren, K.: Introduction to UPC and Language Specification. Tech. Rep. CCS-TR-99-157, George Mason University (1999)"},{"key":"136_CR8","doi-asserted-by":"crossref","unstructured":"Chapman, B.M., Bregier, F., Patil, A., Prabhakar, A.: Achieving performance under OpenMP on ccNUMA and software distributed shared memory systems. In: Concurrency: Practice and Experience, vol. 14, pp. 713\u2013739. John Wiley & Sons (2002)","DOI":"10.1002\/cpe.646"},{"key":"136_CR9","doi-asserted-by":"crossref","unstructured":"Chapman, B.M., Huang, L., Jin, H., Jost, G., de Supinski, B.R.: Extending openmp worksharing directives for multithreading. In: EuroPar\u201906 Parallel Processing (2006)","DOI":"10.1007\/11823285_67"},{"key":"136_CR10","unstructured":"Dolbeau, R., Bihan, S., Bodin, F.: HMPP: A hybrid multi-core parallel programming environment (2007)"},{"key":"136_CR11","doi-asserted-by":"crossref","unstructured":"Duran, A., Perez, J.M., Ayguade, E., Badia, R., Labarta, J.: Extending the openmp tasking model to allow dependant tasks. In: IWOMP Proceedings (2008)","DOI":"10.1007\/978-3-540-79561-2_10"},{"key":"136_CR12","doi-asserted-by":"crossref","unstructured":"Frigo, M., Leiserson, C.E., Randall, K.H.: The implementation of the cilk-5 multithreaded language. In: ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI). Montreal, Canada (1998)","DOI":"10.1145\/277650.277725"},{"key":"136_CR13","doi-asserted-by":"crossref","unstructured":"Goglin, B., Furmento, N.: Enabling High-Performance memory-migration in Linux for multithreaded applications. In: MTAAP\u201909: Workshop on Multithreaded Architectures and Applications, held in conjunction with IPDPS 2009. IEEE Computer Society Press, Rome, Italy (2009). doi: 10.1109\/IPDPS.2009.5161101","DOI":"10.1109\/IPDPS.2009.5161101"},{"key":"136_CR14","unstructured":"hwloc: Portable hardware locality. http:\/\/runtime.bordeaux.inria.fr\/hwloc\/"},{"key":"136_CR15","doi-asserted-by":"crossref","unstructured":"Koelbel, C., Loveman, D., Schreiber, R., Steele, G., Zosel, M.: The high performance Fortran handbook (1994)","DOI":"10.1063\/1.4823319"},{"key":"136_CR16","doi-asserted-by":"crossref","unstructured":"L\u00f6f, H., Holmgren, S.: affinity-on-next-touch: increasing the performance of an industrial PDE solver on a cc-NUMA system. In: 19th ACM International Conference on Supercomputing, pp. 387\u2013392. Cambridge, MA, USA (2005)","DOI":"10.1145\/1088149.1088201"},{"key":"136_CR17","unstructured":"Mami: Marcel memory interface. http:\/\/runtime.bordeaux.inria.fr\/MaMI\/"},{"key":"136_CR18","unstructured":"McCalpin, J.D.: Memory bandwidth and machine balance in current high performance computers. IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter pp. 19\u201325 (1995)"},{"key":"136_CR19","doi-asserted-by":"crossref","unstructured":"Nikolopoulos, D.S., Papatheodorou, T.S., Polychronopoulos, C.D., Labarta, J., AyguadT, E.: User-level dynamic page migration for multiprogrammed shared-memory multiprocessors. In: ICPP, pp. 95\u2013103. IEEE (2000)","DOI":"10.1145\/335231.335243"},{"key":"136_CR20","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1006\/jpdc.2001.1817","volume":"62","author":"D.S. Nikolopoulos","year":"2002","unstructured":"Nikolopoulos D.S., Polychronopoulos C.D., Papatheodorou T.S., Labarta J., Ayguad T.E.: Scheduler-activated dynamic page migration for multiprogrammed DSM multiprocessors. Parallel Distrib. Comput. 62, 1069\u20131103 (2002)","journal-title":"Parallel Distrib. Comput."},{"key":"136_CR21","unstructured":"NordTn, M., L.-f, H., Rantakokko, J., Holmgren, S.: Geographical locality and dynamic data migration for OpenMP implementations of adaptive PDE solvers. In: Second International Workshop on OpenMP (IWOMP 2006). Reims, France (2006)"},{"key":"136_CR22","doi-asserted-by":"crossref","unstructured":"Song, F., Moore, S., Dongarra, J.: Feedback-directed thread scheduling with memory considerations. In: Proceedings of the 16th IEEE International Symposium on High-Performance Distributed Computing (HPDC07). Monterey Bay, CA (2007)","DOI":"10.1145\/1272366.1272380"},{"key":"136_CR23","unstructured":"Steckermeier, M., Bellosa, F.: Using locality information in userlevel scheduling. Tech. Rep. TR-95-14, University of Erlangen-Nnrnberg\u2014Computer Science Department\u2014Operating Systems\u2014IMMD IV, Martensstrab\u0301be 1, 91058 Erlangen, Germany (1995)"},{"key":"136_CR24","doi-asserted-by":"crossref","unstructured":"Terboven, C., an Mey, D., Schmidl, D., Jin, H., Reichstein, T.: Data and thread affinity in openmp programs. In: MAW \u201908: Proceedings of the 2008 workshop on Memory access on future processors, pp. 377\u2013384. ACM, New York, NY, USA (2008). doi: 10.1145\/1366219.1366222","DOI":"10.1145\/1366219.1366222"},{"key":"136_CR25","unstructured":"The OpenMP API specification for parallel programming. http:\/\/www.openmp.org\/"},{"key":"136_CR26","doi-asserted-by":"crossref","unstructured":"Thibault, S., Namyst, R., Wacrenier, P.A.: Building portable thread schedulers for hierarchical multiprocessors: the BubbleSched Framework. In: Euro-Par. ACM, Rennes, France (2007)","DOI":"10.1007\/978-3-540-74466-5_6"},{"key":"136_CR27","unstructured":"Thread Building Blocks. http:\/\/www.intel.com\/software\/products\/tbb\/"},{"key":"136_CR28","doi-asserted-by":"crossref","unstructured":"Yang, R., Antony, J., Janes, P.P., Rendell, A.P.: Memory and thread placement effects as a function of cache usage: a study of the Gaussian chemistry code on the SunFire X4600 M2. In: Proceedings of the International Symposium on Parallel Architectures, Algorithms, and Networks (i-span 2008), pp. 31\u201336 (2008)","DOI":"10.1109\/I-SPAN.2008.13"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-010-0136-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-010-0136-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-010-0136-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T10:14:12Z","timestamp":1685614452000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-010-0136-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,5,30]]},"references-count":28,"journal-issue":{"issue":"5-6","published-print":{"date-parts":[[2010,10]]}},"alternative-id":["136"],"URL":"https:\/\/doi.org\/10.1007\/s10766-010-0136-3","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"value":"0885-7458","type":"print"},{"value":"1573-7640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,5,30]]}}}